GGUF models by larenspear
47 GGUF models quantized by larenspear on Hugging Face. Sizes run from 129M to 34.4B parameters. The longest trained context is 1024K tokens.
About larenspear on Hugging Face
larenspear has published 47 GGUF models that ggufmodels.com tracks, across families such as Yi, Llama and Mamba. The most downloaded are TinyLlama-1.1B-Chat-v1.0, Yi-1.5-6B-Chat and OLMo-7B-Instruct-hf.
The quants larenspear publishes most often are Q2_K (39), Q8_0 (38), Q6_K (38) and Q5_K_M (38). Their Q4_K_M files range from 0.1 to 10.4 GB. Parameter counts run from 129M to 34.4B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has larenspear published?
47 models are listed here, mainly from the Yi, Llama and Mamba families. The most downloaded is TinyLlama-1.1B-Chat-v1.0.
Which quants does larenspear publish?
The most common are Q2_K (39 models), Q8_0 (38 models), Q6_K (38 models) and Q5_K_M (38 models).